When Object Detection Meets Knowledge Distillation: A Survey
IEEE Transactions on Pattern Analysis and Machine Intelligence · 2023-08 · 45 (8) · 10555-10579
DOI: 10.1109/tpami.2023.3257546 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Pattern Analysis and Machine Intelligence, 2023-08. Verfasst von Zhihui Li und 6 weiteren Autor:innen. Die Arbeit wurde bisher 195-mal zitiert (Crossref) und nennt 158 Literaturangaben. Gefördert von: Natural Science Outstanding Youth Fund of Shandong Province, National Natural Science Foundation of China, Young Science and Technology Nova of Shaanxi Province.
Abstract (Originalsprache)
Object detection (OD) is a crucial computer vision task that has seen the development of many algorithms and models over the years. While the performance of current OD models has improved, they have also become more complex, making them impractical for industry applications due to their large parameter size. To tackle this problem, knowledge distillation (KD) technology was proposed in 2015 for image classification and subsequently extended to other visual tasks due to its ability to transfer knowledge learned by complex teacher models to lightweight student models. This paper presents a comprehensive survey of KD-based OD models developed in recent years, with the aim of providing researchers with an overview of recent progress in the field. We conduct an in-depth analysis of existing works, highlighting their advantages and limitations, and explore future research directions to inspire the design of models for related tasks. We summarize the basic principles of designing KD-based OD models, describe related KD-based OD tasks, including performance improvements for lightweight models, catastrophic forgetting in incremental OD, small object detection, and weakly/semi-supervised OD. We also analyze novel distillation techniques, i.e. different types of distillation loss, feature interaction between teacher and student models, etc. Additionally, we provide an overview of the extended applications of KD-based OD models on specific datasets, such as remote sensing images and 3D point cloud datasets. We compare and analyze the performance of different models on several common datasets and discuss promising directions for solving specific OD problems.
Förderung
- Natural Science Outstanding Youth Fund of Shandong Province
- National Natural Science Foundation of China
- Young Science and Technology Nova of Shaanxi Province
- Fundamental Research Funds for the Central Universities
Zitieren
APA
Li, Z., Xu, P., Chang, X., Yang, L., Zhang, Y., Yao, L., & Chen, X. (2023). When Object Detection Meets Knowledge Distillation: A Survey. IEEE Transactions on Pattern Analysis and Machine Intelligence, 45(8), 10555-10579. https://doi.org/10.1109/tpami.2023.3257546
Vancouver
Li Z, Xu P, Chang X, Yang L, Zhang Y, Yao L, et al. When Object Detection Meets Knowledge Distillation: A Survey. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2023;45(8):10555-10579. doi:10.1109/tpami.2023.3257546
BibTeX
@article{Li2023,
author = {Li, Zhihui and Xu, Pengfei and Chang, Xiaojun and Yang, Luyao and Zhang, Yuanyuan and Yao, Lina and Chen, Xiaojiang},
title = {When Object Detection Meets Knowledge Distillation: A Survey},
journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
year = {2023},
volume = {45},
number = {8},
pages = {10555--10579},
doi = {10.1109/tpami.2023.3257546}
}
EUVIMED